© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 6849
    Prev
    Next
    INDEX
    Explanations

    structured data or object representations, particularly key-value pairs and nested structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FontWeight
    -0.78
    ors
    -0.66
     TextAppearance
    -0.66
    IDATE
    -0.64
    hofen
    -0.62
    mente
    -0.61
    tics
    -0.60
    de
    -0.59
    Coll
    -0.58
     מדי
    -0.56
    POSITIVE LOGITS
     autorytatywna
    1.19
    ={
    0.99
    .*")]
    0.97
    verwijspagina
    0.92
    {`
    0.83
    ={[
    0.82
     Prus
    0.81
    ]={
    0.80
    InjectAttribute
    0.80
     Margot
    0.80
    Activations Density 0.063%

    No Known Activations